This study proposes supplementary performance indicators to support approach-level interpretation within the current Smart Intersection System (SIS) evaluation framework, and examines their interpretive characteristics through real-world case studies. While existing Intelligent Transportation System (ITS) performance evaluation standards assess the accuracy at the lane-level direction unit, practical traffic operations often require a comprehensive understanding of the performance at the approach level. To address this limitation, three supplementary indicators were developed: traffic-weighted approach accuracy (TWAA), which reflects the average performance considering traffic exposure; bottleneck-based approach score (BAS), which identifies the lowest-performing lane-level direction unit; and the approach reliability index (ARI), which evaluates the overall operational stability based on threshold compliance. Case study results demonstrate that the proposed indicators provide complementary insights using the same raw data. The TWAA reflects the operational influence of dominant traffic flows. The BAS reveals localized deficiencies that may be masked by average-based measures. The ARI identifies whether the performance is consistently maintained across lane-level direction units. Rather than replacing existing evaluation standards, the proposed indicators serve as a multidimensional framework that enhances the usability of performance data in decision making. These indicators can be applied in a complementary manner depending on the evaluation objectives, such as administrative acceptance, operational efficiency, and maintenance prioritization. Future research should further validate the framework under diverse traffic and geometric conditions, and extend its application to intersection-wide and network-level analyses.

Accurate estimation of vehicle exhaust emissions at urban intersections is essential to assess environmental impacts and support sustainable traffic management. Traditional emission models often rely on aggregated traffic volumes or measures of average speed that fail to capture the dynamic behaviors of vehicles such as acceleration, deceleration, and idling. This study presents a methodology that leverages video data from smart intersections to estimate vehicle emissions at microscale and in real time. Using a CenterNet-based object detection and tracking framework, vehicle trajectories, speeds, and classifications were extracted with high precision. A structured preprocessing pipeline was applied to correct noise, missing frames, and classification inconsistencies to ensure reliable time-series inputs. Subsequently, a lightweight emission model integrating vehicle-specific coefficients was employed to estimate major pollutants including CO and NOx at a framelevel resolution. The proposed algorithm was validated using real-world video data from a smart intersection in Hwaseong, Korea, and the results indicated significant improvements in accuracy compared to conventional approaches based on average speed. In particular, the model reflected variations in emissions effectively under congested conditions and thus captured the elevated impact of frequent stopand- go patterns. Beyond technical performance, these results demonstrate that traffic video data, which have traditionally been limited to flow monitoring and safety analysis, can be extended to practical environmental evaluation. The proposed algorithm offers a scalable and cost-effective tool for urban air quality management, which enables policymakers and practitioners to link traffic operations with emission outcomes in a quantifiable manner.